石油化工高等学校学报

石油化工高等学校学报 ›› 2023, Vol. 36 ›› Issue (6): 57-63.DOI: 10.12422/j.issn.1006-396X.2023.06.006

• 研究与开发 • 上一篇    下一篇

用于红外宽带吸收器的深度学习网络模型框架

王璇(), 冯乃星, 张玉贤()   

  1. 安徽大学 教育部智能计算与信号处理重点实验室/信息材料与智能传感实验室,安徽 合肥 230601
  • 收稿日期:2023-10-17 修回日期:2023-12-06 出版日期:2023-12-25 发布日期:2024-01-03
  • 通讯作者: 张玉贤
  • 作者简介:王璇(1997⁃),女,硕士研究生,从事人工超材料优化设计方面的研究;E⁃mail:p21201014@stu.ahu.edu.cn
  • 基金资助:
    国家自然科学青年基金项目(62101333)

Deep Learning Neural Network Modeling Framework for Infrared Broadband Absorbers

Xuan WANG(), Naixing FENG, Yuxian ZHANG()   

  1. Key Laboratory of Intelligent Computing and Signal Processing,Ministry of Education,Information Materials and Intelligent Sensing Laboratory of Anhui Province,Anhui University,Hefei Anhui 230601,China
  • Received:2023-10-17 Revised:2023-12-06 Published:2023-12-25 Online:2024-01-03
  • Contact: Yuxian ZHANG

摘要:

揭示复杂的光物质相互作用,必须简化超材料的正向和反向按需设计。近年来深度学习作为一种流行的数据驱动方法,在很大程度上缓解了数值模拟耗时长、重经验的特点。提出了一种基于全连接的深度神经网络框架实现宽带吸收器的逆向设计和光谱预测。结果表明,深度神经网络(DNN)模型的准确度为87.47%;与传统的数值算法相比,该模型不仅在确保精确度的同时获得更高的效率,而且可为超材料按需设计性能提供参考。

关键词: 逆设计问题, 石墨烯, 黑磷, 深度学习, 宽带吸收

Abstract:

To reveal complex light?matter interactions, it is necessary to simplify the on?demand design of metamaterials for both forward and inverse applications. Deep learning, a popular data?driven approach, has recently alleviated to a large extent the time?consuming and empirical nature of widely used numerical simulations.A fully?connected deep neural network?based framework for inverse design and spectral prediction of broadband absorbers was proposed.The results demonstrate and validate the high accuracy of the proposed DNN model at 87.47%.The model not only outperform traditional numerical algorithms while ensuring accuracy, but also provides an important reference for on?demand design performance of metamaterials.

Key words: Inverse design problem, Graphene, Black phosphorus, Deep learning, Broadband absorption

中图分类号: 

引用本文

王璇, 冯乃星, 张玉贤. 用于红外宽带吸收器的深度学习网络模型框架[J]. 石油化工高等学校学报, 2023, 36(6): 57-63.

Xuan WANG, Naixing FENG, Yuxian ZHANG. Deep Learning Neural Network Modeling Framework for Infrared Broadband Absorbers[J]. Journal of Petrochemical Universities, 2023, 36(6): 57-63.

使用本文